Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 821 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1836. Min Act: -0.0001

Data Index: 1491320 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1815. Min Act: -0.0002

Data Index: 505285 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1675. Min Act: -0.0001

Data Index: 676308 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1599. Min Act: -0.0001

Data Index: 523299 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1657. Min Act: -0.0001

Data Index: 655892 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1507. Min Act: -0.0002

Data Index: 1063630 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1490. Min Act: -0.0002

Data Index: 763302 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1583. Min Act: -0.0002

Data Index: 980062 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1652. Min Act: -0.0001

Data Index: 259308 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1557. Min Act: -0.0001

Data Index: 571091 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1536. Min Act: -0.0002

Data Index: 993002 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1523. Min Act: -0.0002

Data Index: 564993 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1582. Min Act: -0.0002

Data Index: 1055896 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1418. Min Act: -0.0001

Data Index: 550723 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1454. Min Act: -0.0001

Data Index: 1086961 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1439. Min Act: -0.0002

Data Index: 123872 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1004421 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1440. Min Act: -0.0001

Data Index: 42502 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1436. Min Act: -0.0002

Data Index: 792207 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1420. Min Act: -0.0002

Data Index: 937396 (C4 (Web Text))

Max Activating Token Index: 605